• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.3
• /
• pp.247-252
• /
• 2017

The purpose of this study is to suggest the visual teaching method for the English vowel pronunciation, especially for the hearing-impaired who mostly rely on the visual aids, based on the SVM technique. By extracting phonetic features using the SVM technique from the sounds that are hard to hear by ear, the lip shapes for each vowel were refined. The lip shape refinement for vowels is advantageous in that language learners can easily see the movement of articulators by eye, and it is helpful for learning and teaching English vowels for the hearing-impaired.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.47-54
• /
• 2013

In this paper, analyze the technical elements of the CTI system to design the proposed system, understand the requirements of CTI IP based system. in the Hearing-Impaired designed a CTI system of mobile phone-based services available to the CTI call center system based on this. Furthermore, we implemented voiceXML scenario data analysis modules using the JAVA language to implement the system was designed, the server provides. And an implementation of the CTI system of mobile phone base for the Hearing-Impaired by integrating the modules that have been implemented. Finally, create a scenario that uses the CTI system for mobile base to test and evaluation, based on the test scenario each functional, we conducted repeated tests. It was possible to confirm the results of time for the acquisition of the test result information has been reduced about 20 seconds on average than the audio system based on conventional.

• Korean Journal of Social Welfare
• /
• v.60 no.3
• /
• pp.83-106
• /
• 2008

The Purpose of this study is to explore if people with intellectual disabilities can play a role as 'meaningful informants' in research process in Korea, by challenging the existing paradigm which consists of suspicion on the communication ability of people with intellectual disabilities and truthlessness of their statements, which results in ignorance on the covered life of people with intellectual disabilities. In this research, lessons which could learn through reinterpretation of my research experience are as follows. Firstly, the deficits of communication ability can be supplemented with restructuring interview instruments such as research questions, visual aids etc and adopting conversation analysis methods. Secondly, Suspicion on the truthlessness of their statements can be restructured by epistemological and methodological reinterpretation on the representation of social reality. Thirdly, the mechanism of exclusion and oppression according to the ignorance can be substituted by 'uncovering the life of people with intellectual disabilities', which can be basis of reconstructing the contents of programmes in the disability service centers and disability policies in the government. With these research results it could be argued that there needs to include people with intellectual disabilities as meaningful informants in the research projects funded by the government and also to provide people with intellectual disabilities with diverse roles in the research process by virtue of the development of qualitative research methods in the near future.

• 재활복지
• /
• v.21 no.2
• /
• pp.233-246
• /
• 2017

The present study is a basic study for application of Augmented Reality (AR) to verb teaching for children with language developmental disorders and is intended to examine validity for the list of verbs at the beginning of development. To confirm the validity of the verbs list, the appropriateness of the verbs was evaluated by three professors with certification of KSLP (Korean Speech-Language Pathologist) working in the department of Speech-Language Pathology at the university. The motion validity test was conducted by showing motion implemented as AR to eight master's students in Speech-Language Pathology major, having them record verbs that came to their mind, and evaluating in the conformity. The second motion validity test was conducted by using 5-point Likert scales to 87 undergraduates in Speech-Language Pathology major and having them see the motions in AR and marked the degrees to which them see the motions conform to the relevant verbs on the scales. Using the SPSS 21.0 program, descriptive statics analyses of the results were conducted. Through this all process, thirty verbs were selected as having content validity. It could be seen that when AR based communication system are applied, things and backgrounds that complement the insufficient movements of motions and help motion recognition should be also provided. In future studies, the 3D images of the AR based communication system will be complemented and the content validity will be verified with typically developing children and the children with language developmental disorders.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.125-144
• /
• 2023

Recently, the use of Large Language Models (LLMs) such as ChatGPT has been increasing in various fields such as interactive commerce and mobile financial services. However, LMMs, which are mainly created by learning existing documents, can also learn various human biases inherent in documents. Nevertheless, there have been few comparative studies on the aspects of bias and discrimination in LLMs. The purpose of this study is to examine the existence and extent of nine types of discrimination (Age, Disability status, Gender identity, Nationality, Physical appearance, Race ethnicity, Religion, Socio-economic status, Sexual orientation) in LLMs and suggest ways to improve them. For this purpose, we utilized BBQ (Bias Benchmark for QA), a tool for identifying discrimination, to compare three large-scale language models including ChatGPT, GPT-3, and Bing Chat. As a result of the evaluation, a large number of discriminatory responses were observed in the mega-language models, and the patterns differed depending on the mega-language model. In particular, problems were exposed in elder discrimination and disability discrimination, which are not traditional AI ethics issues such as sexism, racism, and economic inequality, and a new perspective on AI ethics was found. Based on the results of the comparison, this paper describes how to improve and develop large-scale language models in the future.

• Journal of Digital Convergence
• /
• v.14 no.3
• /
• pp.1-12
• /
• 2016

The definition of digital poverty has not been changed since it was used at the first digital divide survey in 2000s. The objective of this study is to reexamine and redefine digital poverty targets of digital divide survey. This study examines the present state for the target of the digital divide survey focusing on Disabilities, Low-Income and Elders and then redefines digital poverty for them. The results suggest to reexamine 15 types of disabilities by the revised the Disabled Welfare Law as digital divide targets, rather than limiting to physical, brain, hearing and visual disabilities. For the low-income target, people on the second-to-the bottom income bracket as well as those on basic welfare should be included as the target of low-income people for digital poverty. The age of the elder target for digital poverty should be adjusted to sixty-five or more in the era of aging population.

• The KIPS Transactions:PartB
• /
• v.13B no.5 s.108
• /
• pp.569-578
• /
• 2006

The present study implemented AAC(Augmentative and Alternative Communication) system using images that speech defectives can easily understand. In particular, the implementation was focused on the portability and mobility of the AAC system as well as communication system of a more flexible form. For mobility and portability, we implemented a system operable in mobile devices such as PDA so that speech defectives can communicate as food as ordinary People at any Place using the system Moreover, in order to overcome the limitation of storage space for a large volume of image data, we implemented the AAC system in client/server structure in mobile environment. What is more, for more flexible communication, we built an image dictionary by taking verbs as the base and sub-categorizing nouns according to their corresponding verbs, and regularized the types of sentences generated according to the type of verb, centering on verbs that play the most important role in composing a sentence.

• Phonetics and Speech Sciences
• /
• v.6 no.4
• /
• pp.141-148
• /
• 2014

Voice is the most common means for communication, but some people have difficulties in generating voice due to their congenital or acquired disorders. Individuals with speech disorders might lose their speaking ability due to hearing impairment, encephalopathy or cerebral palsy accompanied by motor skill impairments, or autism caused by mental problems. However, they have needs for communication, so some of them use various types of AAC (Augmentative & Alternative Communication) devices in order to meet their communication needs. In this paper, a mobile application for literate people having speech disorder was designed and implemented by developing accurate and fast sentence-completion functions for efficient user interaction. From a user study and the previous study on Korean text-based communication for adults having difficulty in speech communication, we identified functionality and usability requirements. Specifically, the user interface with scanning features was designed by considering the users' motor skills in using the touch-screen of a mobile device. Finally, we conducted the usability test for the application. The results of the usability test show that the application is easy to learn and efficient to use in communication with people with speech disorders.

• Journal of Korea Multimedia Society
• /
• v.8 no.9
• /
• pp.1248-1257
• /
• 2005

This paper designs and implements a sentence generation for an augmentive and alternative communication system(AAC). The AAC system is assistive communication device to help the mute language disorder communicate more freely and the system have an objected to reduce time and keystrokes for sentence generating. The paper of sentence generation make up for merits and demerits in the existing sentence generation method and in order to sentence generation. One aspect of Korean language that confines nouns defending on the verbs or postpositional words is used for sentence generation. The distinctive feature of this paper is to connect verbs to nouns using domain knowledge. We utilize the lexical information that exploits characteristics of Korean language for sentence generation. A comparison with other approaches is also presented. This sentence generation is based on lexical information by extracting characteristics of sentences.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.169-173
• /
• 2015

현재 스마트폰이나 태블릿PC 등의 터치화면 상에서 사용되는 한글 입력 방식은 qwerty, 나랏글, 천지인 등 시각 정보를 기반으로 만들어진 가상 키보드들이 사용되고 있다. 이는 시각에 문제가 없는 일반인 사용자에게는 효율적인 방식이지만 시각 장애인(시력장애, 시야 결손장애)들에게는 불편한 점이 있다. 이 문제를 개선하기 위하여 터치화면 상에서 손동작을 기반으로 한 한글 입력 방식을 제안한다. 이 방식은 사용자가 직접 기준 위치를 정하여 사용하므로 시각 정보가 제한된 상황에서도 입력할 수 있다. 또한, 이 방식은 사용자가 쉽게 배울 수 있도록 설계되었다. 모음 입력은 사용자가 쉽게 연상 되는 동작에 할당하였고, 자음 입력은 빈도수를 고려하여 자주 사용되는 자음은 편하게 움직일 수 있는 검지와 중지의 움직임에 주로 할당하였다.